Merge branch 'master' of github.com:rg3/youtube-dl into youtube-dl

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.15*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.24*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.09.15**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.09.24**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.09.15
+[debug] youtube-dl version 2016.09.24
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

ChangeLog

@@ -1,8 +1,63 @@
-version <unreleased>
+vesion <unreleased>
+
+Core
++ Improved support for HTML5 subtitles
 
 Extractors
++ [twitter] Support Periscope embeds (#10737)
++ [openload] Support subtitles (#10625)
+
+
+version 2016.09.24
+
+Core
++ Add support for watchTVeverywhere.com authentication provider based MSOs for
+  Adobe Pass authentication (#10709)
+
+Extractors
++ [soundcloud:playlist] Provide video id for early playlist entries (#10733)
++ [prosiebensat1] Add support for kabeleinsdoku (#10732)
+* [cbs] Extract info from thunder videoPlayerService (#10728)
+* [openload] Fix extraction (#10408)
++ [ustream] Support the new HLS streams (#10698)
++ [ooyala] Extract all HLS formats
++ [cartoonnetwork] Add support for Adobe Pass authentication
++ [soundcloud] Extract license metadata
++ [fox] Add support for Adobe Pass authentication (#8584)
++ [tbs] Add support for Adobe Pass authentication (#10642, #10222)
++ [trutv] Add support for Adobe Pass authentication (#10519)
++ [turner] Add support for Adobe Pass authentication
+
+
+version 2016.09.19
+
+Extractors
++ [crunchyroll] Check if already authenticated (#10700)
+- [twitch:stream] Remove fallback to profile extraction when stream is offline
+* [thisav] Improve title extraction (#10682)
+* [vyborymos] Improve station info extraction
+
+
+version 2016.09.18
+
+Core
++ Introduce manifest_url and fragments fields in formats dictionary for
+  fragmented media
++ Provide manifest_url field for DASH segments, HLS and HDS
++ Provide fragments field for DASH segments
+* Rework DASH segments downloader to use fragments field
++ Add helper method for Wowza Streaming Engine formats extraction
+
+Extractors
++ [vyborymos] Add extractor for vybory.mos.ru (#10692)
++ [xfileshare] Add title regular expression for streamin.to (#10646)
++ [globo:article] Add support for multiple videos (#10653)
 + [thisav] Recognize HTML5 videos (#10447)
 * [jwplatform] Improve JWPlayer detection
++ [mangomolo] Add support for Mangomolo embeds
++ [toutv] Add support for authentication (#10669)
+* [franceinter] Fix upload date extraction
+* [tv4] Fix HLS and HDS formats extraction (#10659)
 
 
 version 2016.09.15

Makefile

@@ -1,7 +1,7 @@
 all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
 	find . -name "*.class" -delete
 

docs/supportedsites.md

@@ -388,6 +388,8 @@
  - **mailru**: Видео@Mail.Ru
  - **MakersChannel**
  - **MakerTV**
+ - **mangomolo:live**
+ - **mangomolo:video**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
@@ -849,6 +851,7 @@
  - **VRT**
  - **vube**: Vube.com
  - **VuClip**
+ - **VyboryMos**
  - **Walla**
  - **washingtonpost**
  - **washingtonpost:article**

youtube_dl/downloader/hls.py

@@ -31,7 +31,7 @@ class HlsFD(FragmentFD):
     FD_NAME = 'hlsnative'
 
     @staticmethod
-    def can_download(manifest):
+    def can_download(manifest, info_dict):
         UNSUPPORTED_FEATURES = (
             r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)',  # encrypted streams [1]
             r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [2]
@@ -53,6 +53,7 @@ class HlsFD(FragmentFD):
         )
         check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
         check_results.append(can_decrypt_frag or '#EXT-X-KEY:METHOD=AES-128' not in manifest)
+        check_results.append(not info_dict.get('is_live'))
         return all(check_results)
 
     def real_download(self, filename, info_dict):
@@ -62,7 +63,7 @@ class HlsFD(FragmentFD):
 
         s = manifest.decode('utf-8', 'ignore')
 
-        if not self.can_download(s):
+        if not self.can_download(s, info_dict):
             self.report_warning(
                 'hlsnative has detected features it does not support, '
                 'extraction will be delegated to ffmpeg')

youtube_dl/extractor/brightcove.py

@@ -621,15 +621,21 @@ class BrightcoveNewIE(InfoExtractor):
                     'url': text_track['src'],
                 })
 
+        is_live = False
+        duration = float_or_none(json_data.get('duration'), 1000)
+        if duration and duration < 0:
+            is_live = True
+
         return {
             'id': video_id,
-            'title': title,
+            'title': self._live_title(title) if is_live else title,
             'description': clean_html(json_data.get('description')),
             'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
-            'duration': float_or_none(json_data.get('duration'), 1000),
+            'duration': duration,
             'timestamp': parse_iso8601(json_data.get('published_at')),
             'uploader_id': account_id,
             'formats': formats,
             'subtitles': subtitles,
             'tags': json_data.get('tags', []),
+            'is_live': is_live,
         }

youtube_dl/extractor/cartoonnetwork.py

@@ -33,4 +33,10 @@ class CartoonNetworkIE(TurnerBaseIE):
                     'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big',
                     'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
                 },
+            }, {
+                'url': url,
+                'site_name': 'CartoonNetwork',
+                'auth_required': self._search_regex(
+                    r'_cnglobal\.cvpFullOrPreviewAuth\s*=\s*(true|false);',
+                    webpage, 'auth required', default='false') == 'true',
             })

youtube_dl/extractor/cbs.py

@@ -4,7 +4,9 @@ from .theplatform import ThePlatformFeedIE
 from ..utils import (
     int_or_none,
     find_xpath_attr,
-    ExtractorError,
+    xpath_element,
+    xpath_text,
+    update_url_query,
 )
 
 
@@ -47,27 +49,49 @@ class CBSIE(CBSBaseIE):
         'only_matching': True,
     }]
 
-    def _extract_video_info(self, guid):
+    def _extract_video_info(self, content_id):
-        path = 'dJ5BDC/media/guid/2198311517/' + guid
+        items_data = self._download_xml(
-        smil_url = 'http://link.theplatform.com/s/%s?mbr=true' % path
+            'http://can.cbs.com/thunder/player/videoPlayerService.php',
-        formats, subtitles = self._extract_theplatform_smil(smil_url + '&manifest=m3u', guid)
+            content_id, query={'partner': 'cbs', 'contentId': content_id})
-        for r in ('OnceURL&formats=M3U', 'HLS&formats=M3U', 'RTMP', 'WIFI', '3G'):
+        video_data = xpath_element(items_data, './/item')
-            try:
+        title = xpath_text(video_data, 'videoTitle', 'title', True)
-                tp_formats, _ = self._extract_theplatform_smil(smil_url + '&assetTypes=' + r, guid, 'Downloading %s SMIL data' % r.split('&')[0])
+        tp_path = 'dJ5BDC/media/guid/2198311517/%s' % content_id
-                formats.extend(tp_formats)
+        tp_release_url = 'http://link.theplatform.com/s/' + tp_path
-            except ExtractorError:
+
+        asset_types = []
+        subtitles = {}
+        formats = []
+        for item in items_data.findall('.//item'):
+            asset_type = xpath_text(item, 'assetType')
+            if not asset_type or asset_type in asset_types:
                 continue
+            asset_types.append(asset_type)
+            query = {
+                'mbr': 'true',
+                'assetTypes': asset_type,
+            }
+            if asset_type.startswith('HLS') or asset_type in ('OnceURL', 'StreamPack'):
+                query['formats'] = 'MPEG4,M3U'
+            elif asset_type in ('RTMP', 'WIFI', '3G'):
+                query['formats'] = 'MPEG4,FLV'
+            tp_formats, tp_subtitles = self._extract_theplatform_smil(
+                update_url_query(tp_release_url, query), content_id,
+                'Downloading %s SMIL data' % asset_type)
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
         self._sort_formats(formats)
-        metadata = self._download_theplatform_metadata(path, guid)
+
-        info = self._parse_theplatform_metadata(metadata)
+        info = self._extract_theplatform_metadata(tp_path, content_id)
         info.update({
-            'id': guid,
+            'id': content_id,
+            'title': title,
+            'series': xpath_text(video_data, 'seriesTitle'),
+            'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
+            'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
+            'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
+            'thumbnail': xpath_text(video_data, 'previewImageURL'),
             'formats': formats,
             'subtitles': subtitles,
-            'series': metadata.get('cbs$SeriesTitle'),
-            'season_number': int_or_none(metadata.get('cbs$SeasonNumber')),
-            'episode': metadata.get('cbs$EpisodeTitle'),
-            'episode_number': int_or_none(metadata.get('cbs$EpisodeNumber')),
         })
         return info
 

youtube_dl/extractor/cbsnews.py

@@ -9,6 +9,7 @@ from ..utils import (
 
 
 class CBSNewsIE(CBSIE):
+    IE_NAME = 'cbsnews'
     IE_DESC = 'CBS News'
     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
 
@@ -68,15 +69,16 @@ class CBSNewsIE(CBSIE):
 
 
 class CBSNewsLiveVideoIE(InfoExtractor):
+    IE_NAME = 'cbsnews:livevideo'
     IE_DESC = 'CBS News Live Videos'
-    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[^/?#]+)'
 
     # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
     _TEST = {
         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
         'info_dict': {
             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Clinton, Sanders Prepare To Face Off In NH',
             'duration': 334,
         },
@@ -84,25 +86,22 @@ class CBSNewsLiveVideoIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        display_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        video_info = self._download_json(
+            'http://feeds.cbsn.cbsnews.com/rundown/story', display_id, query={
+                'device': 'desktop',
+                'dvr_slug': display_id,
+            })
 
-        video_info = self._parse_json(self._html_search_regex(
+        formats = self._extract_akamai_formats(video_info['url'], display_id)
-            r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
+        self._sort_formats(formats)
-
-        hdcore_sign = 'hdcore=3.3.1'
-        f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
-        if f4m_formats:
-            for entry in f4m_formats:
-                # URLs without the extra param induce an 404 error
-                entry.update({'extra_param_to_segment_url': hdcore_sign})
-        self._sort_formats(f4m_formats)
 
         return {
-            'id': video_id,
+            'id': display_id,
+            'display_id': display_id,
             'title': video_info['headline'],
             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
             'duration': parse_duration(video_info.get('segmentDur')),
-            'formats': f4m_formats,
+            'formats': formats,
         }

youtube_dl/extractor/common.py

@@ -1828,7 +1828,7 @@ class InfoExtractor(object):
                 for track_tag in re.findall(r'<track[^>]+>', media_content):
                     track_attributes = extract_attributes(track_tag)
                     kind = track_attributes.get('kind')
-                    if not kind or kind == 'subtitles':
+                    if not kind or kind in ('subtitles', 'captions'):
                         src = track_attributes.get('src')
                         if not src:
                             continue
@@ -1836,16 +1836,21 @@ class InfoExtractor(object):
                         media_info['subtitles'].setdefault(lang, []).append({
                             'url': absolute_url(src),
                         })
-            if media_info['formats']:
+            if media_info['formats'] or media_info['subtitles']:
                 entries.append(media_info)
         return entries
 
     def _extract_akamai_formats(self, manifest_url, video_id):
         formats = []
+        hdcore_sign = 'hdcore=3.7.0'
         f4m_url = re.sub(r'(https?://.+?)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
-        formats.extend(self._extract_f4m_formats(
+        if 'hdcore=' not in f4m_url:
-            update_url_query(f4m_url, {'hdcore': '3.7.0'}),
+            f4m_url += ('&' if '?' in f4m_url else '?') + hdcore_sign
-            video_id, f4m_id='hds', fatal=False))
+        f4m_formats = self._extract_f4m_formats(
+            f4m_url, video_id, f4m_id='hds', fatal=False)
+        for entry in f4m_formats:
+            entry.update({'extra_param_to_segment_url': hdcore_sign})
+        formats.extend(f4m_formats)
         m3u8_url = re.sub(r'(https?://.+?)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
         formats.extend(self._extract_m3u8_formats(
             m3u8_url, video_id, 'mp4', 'm3u8_native',

youtube_dl/extractor/crunchyroll.py

@@ -46,6 +46,13 @@ class CrunchyrollBaseIE(InfoExtractor):
         login_page = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login page')
 
+        def is_logged(webpage):
+            return '<title>Redirecting' in webpage
+
+        # Already logged in
+        if is_logged(login_page):
+            return
+
         login_form_str = self._search_regex(
             r'(?P<form><form[^>]+?id=(["\'])%s\2[^>]*>)' % self._LOGIN_FORM,
             login_page, 'login form', group='form')
@@ -69,7 +76,7 @@ class CrunchyrollBaseIE(InfoExtractor):
             headers={'Content-Type': 'application/x-www-form-urlencoded'})
 
         # Successful login
-        if '<title>Redirecting' in response:
+        if is_logged(response):
             return
 
         error = self._html_search_regex(

youtube_dl/extractor/extractors.py

@@ -516,6 +516,7 @@ from .movingimage import MovingImageIE
 from .msn import MSNIE
 from .mtv import (
     MTVIE,
+    MTVVideoIE,
     MTVServicesEmbeddedIE,
     MTVDEIE,
 )
@@ -1069,6 +1070,7 @@ from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
+from .vyborymos import VyboryMosIE
 from .walla import WallaIE
 from .washingtonpost import (
     WashingtonPostIE,

youtube_dl/extractor/fox.py

@@ -1,14 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+from .adobepass import AdobePassIE
 from ..utils import (
     smuggle_url,
     update_url_query,
 )
 
 
-class FOXIE(InfoExtractor):
+class FOXIE(AdobePassIE):
     _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.fox.com/watch/255180355939/7684182528',
@@ -30,14 +30,26 @@ class FOXIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        release_url = self._parse_json(self._search_regex(
+        settings = self._parse_json(self._search_regex(
-            r'"fox_pdk_player"\s*:\s*({[^}]+?})', webpage, 'fox_pdk_player'),
+            r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
-            video_id)['release_url']
+            webpage, 'drupal settings'), video_id)
+        fox_pdk_player = settings['fox_pdk_player']
+        release_url = fox_pdk_player['release_url']
+        query = {
+            'mbr': 'true',
+            'switch': 'http'
+        }
+        if fox_pdk_player.get('access') == 'locked':
+            ap_p = settings['foxAdobePassProvider']
+            rating = ap_p.get('videoRating')
+            if rating == 'n/a':
+                rating = None
+            resource = self._get_mvpd_resource('fbc-fox', None, ap_p['videoGUID'], rating)
+            query['auth'] = self._extract_mvpd_auth(url, video_id, 'fbc-fox', resource)
 
         return {
             '_type': 'url_transparent',
             'ie_key': 'ThePlatform',
-            'url': smuggle_url(update_url_query(
+            'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
-                release_url, {'switch': 'http'}), {'force_smil_url': True}),
             'id': video_id,
         }

youtube_dl/extractor/globo.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import random
+import re
 import math
 
 from .common import InfoExtractor
@@ -14,6 +15,7 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    orderedSet,
     str_or_none,
 )
 
@@ -63,6 +65,9 @@ class GloboIE(InfoExtractor):
     }, {
         'url': 'http://canaloff.globo.com/programas/desejar-profundo/videos/4518560.html',
         'only_matching': True,
+    }, {
+        'url': 'globo:3607726',
+        'only_matching': True,
     }]
 
     class MD5(object):
@@ -396,7 +401,7 @@ class GloboIE(InfoExtractor):
 
 
 class GloboArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)(?:\.html)?'
+    _VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/.]+)(?:\.html)?'
 
     _VIDEOID_REGEXES = [
         r'\bdata-video-id=["\'](\d{7,})',
@@ -408,15 +413,20 @@ class GloboArticleIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
-        'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
         'info_dict': {
-            'id': '3652183',
+            'id': 'novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes',
-            'ext': 'mp4',
+            'title': 'Novidade na fiscalização de bagagem pela Receita provoca discussões',
-            'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
+            'description': 'md5:c3c4b4d4c30c32fce460040b1ac46b12',
-            'duration': 110.711,
+        },
-            'uploader': 'Rede Globo',
+        'playlist_count': 1,
-            'uploader_id': '196',
+    }, {
-        }
+        'url': 'http://g1.globo.com/pr/parana/noticia/2016/09/mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato.html',
+        'info_dict': {
+            'id': 'mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato',
+            'title': "Lula era o 'comandante máximo' do esquema da Lava Jato, diz MPF",
+            'description': 'md5:8aa7cc8beda4dc71cc8553e00b77c54c',
+        },
+        'playlist_count': 6,
     }, {
         'url': 'http://gq.globo.com/Prazeres/Poder/noticia/2015/10/all-o-desafio-assista-ao-segundo-capitulo-da-serie.html',
         'only_matching': True,
@@ -435,5 +445,12 @@ class GloboArticleIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
+        video_ids = []
-        return self.url_result('globo:%s' % video_id, 'Globo')
+        for video_regex in self._VIDEOID_REGEXES:
+            video_ids.extend(re.findall(video_regex, webpage))
+        entries = [
+            self.url_result('globo:%s' % video_id, GloboIE.ie_key())
+            for video_id in orderedSet(video_ids)]
+        title = self._og_search_title(webpage, fatal=False)
+        description = self._html_search_meta('description', webpage)
+        return self.playlist_result(entries, display_id, title, description)

youtube_dl/extractor/mtv.py

@@ -270,6 +270,29 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
 
 
 class MTVIE(MTVServicesInfoExtractor):
+    IE_NAME = 'mtv'
+    _VALID_URL = r'https?://(?:www\.)?mtv\.com/(video-clips|full-episodes)/(?P<id>[^/?#.]+)'
+    _FEED_URL = 'http://www.mtv.com/feeds/mrss/'
+
+    _TESTS = [{
+        'url': 'http://www.mtv.com/video-clips/vl8qof/unlocking-the-truth-trailer',
+        'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
+        'info_dict': {
+            'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
+            'ext': 'mp4',
+            'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
+            'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
+            'timestamp': 1468846800,
+            'upload_date': '20160718',
+        },
+    }, {
+        'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101',
+        'only_matching': True,
+    }]
+
+
+class MTVVideoIE(MTVServicesInfoExtractor):
+    IE_NAME = 'mtv:video'
     _VALID_URL = r'''(?x)^https?://
         (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|
            m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))'''

youtube_dl/extractor/mwave.py

@@ -9,9 +9,9 @@ from ..utils import (
 
 
 class MwaveIE(InfoExtractor):
-    _VALID_URL = r'https?://mwave\.interest\.me/mnettv/videodetail\.m\?searchVideoDetailVO\.clip_id=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://mwave\.interest\.me/(?:[^/]+/)?mnettv/videodetail\.m\?searchVideoDetailVO\.clip_id=(?P<id>[0-9]+)'
     _URL_TEMPLATE = 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=%s'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=168859',
         # md5 is unstable
         'info_dict': {
@@ -23,7 +23,10 @@ class MwaveIE(InfoExtractor):
             'duration': 206,
             'view_count': int,
         }
-    }
+    }, {
+        'url': 'http://mwave.interest.me/en/mnettv/videodetail.m?searchVideoDetailVO.clip_id=176199',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -60,8 +63,8 @@ class MwaveIE(InfoExtractor):
 
 
 class MwaveMeetGreetIE(InfoExtractor):
-    _VALID_URL = r'https?://mwave\.interest\.me/meetgreet/view/(?P<id>\d+)'
+    _VALID_URL = r'https?://mwave\.interest\.me/(?:[^/]+/)?meetgreet/view/(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://mwave.interest.me/meetgreet/view/256',
         'info_dict': {
             'id': '173294',
@@ -72,7 +75,10 @@ class MwaveMeetGreetIE(InfoExtractor):
             'duration': 3634,
             'view_count': int,
         }
-    }
+    }, {
+        'url': 'http://mwave.interest.me/en/meetgreet/view/256',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/ooyala.py

@@ -47,7 +47,7 @@ class OoyalaBaseIE(InfoExtractor):
                 delivery_type = stream['delivery_type']
                 if delivery_type == 'hls' or ext == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
-                        s_url, embed_code, 'mp4', 'm3u8_native',
+                        re.sub(r'/ip(?:ad|hone)/', '/all/', s_url), embed_code, 'mp4', 'm3u8_native',
                         m3u8_id='hls', fatal=False))
                 elif delivery_type == 'hds' or ext == 'f4m':
                     formats.extend(self._extract_f4m_formats(

youtube_dl/extractor/openload.py

@@ -24,6 +24,22 @@ class OpenloadIE(InfoExtractor):
             'title': 'skyrim_no-audio_1080.mp4',
             'thumbnail': 're:^https?://.*\.jpg$',
         },
+    }, {
+        'url': 'https://openload.co/embed/rjC09fkPLYs',
+        'info_dict': {
+            'id': 'rjC09fkPLYs',
+            'ext': 'mp4',
+            'title': 'movie.mp4',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'subtitles': {
+                'en': [{
+                    'ext': 'vtt',
+                }],
+            },
+        },
+        'params': {
+            'skip_download': True,  # test subtitles only
+        },
     }, {
         'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
         'only_matching': True,
@@ -51,7 +67,8 @@ class OpenloadIE(InfoExtractor):
         # declared to be freely used in youtube-dl
         # See https://github.com/rg3/youtube-dl/issues/10408
         enc_data = self._html_search_regex(
-            r'<span[^>]+id="hiddenurl"[^>]*>([^<]+)</span>', webpage, 'encrypted data')
+            r'<span[^>]*>([^<]+)</span>\s*<span[^>]*>[^<]+</span>\s*<span[^>]+id="streamurl"',
+            webpage, 'encrypted data')
 
         video_url_chars = []
 
@@ -60,7 +77,7 @@ class OpenloadIE(InfoExtractor):
             if j >= 33 and j <= 126:
                 j = ((j + 14) % 94) + 33
             if idx == len(enc_data) - 1:
-                j += 3
+                j += 2
             video_url_chars += compat_chr(j)
 
         video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)
@@ -70,11 +87,17 @@ class OpenloadIE(InfoExtractor):
             'title', default=None) or self._html_search_meta(
             'description', webpage, 'title', fatal=True)
 
-        return {
+        entries = self._parse_html5_media_entries(url, webpage, video_id)
+        subtitles = entries[0]['subtitles'] if entries else None
+
+        info_dict = {
             'id': video_id,
             'title': title,
             'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'url': video_url,
             # Seems all videos have extensions in their titles
             'ext': determine_ext(title),
+            'subtitles': subtitles,
         }
+
+        return info_dict

youtube_dl/extractor/periscope.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     parse_iso8601,
@@ -41,6 +43,13 @@ class PeriscopeIE(PeriscopeBaseIE):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src=([\'"])(?P<url>(?:https?:)?//(?:www\.)?periscope\.tv/(?:(?!\1).)+)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
     def _real_extract(self, url):
         token = self._match_id(url)
 

youtube_dl/extractor/prosiebensat1.py

@@ -122,7 +122,17 @@ class ProSiebenSat1BaseIE(InfoExtractor):
 class ProSiebenSat1IE(ProSiebenSat1BaseIE):
     IE_NAME = 'prosiebensat1'
     IE_DESC = 'ProSiebenSat.1 Digital'
-    _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany|7tv)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            (?:
+                                prosieben(?:maxx)?|sixx|sat1(?:gold)?|kabeleins(?:doku)?|the-voice-of-germany|7tv|advopedia
+                            )\.(?:de|at|ch)|
+                            ran\.de|fem\.com|advopedia\.de
+                        )
+                        /(?P<id>.+)
+                    '''
 
     _TESTS = [
         {
@@ -290,6 +300,24 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
                 'skip_download': True,
             },
         },
+        {
+            # geo restricted to Germany
+            'url': 'http://www.kabeleinsdoku.de/tv/mayday-alarm-im-cockpit/video/102-notlandung-im-hudson-river-ganze-folge',
+            'only_matching': True,
+        },
+        {
+            # geo restricted to Germany
+            'url': 'http://www.sat1gold.de/tv/edel-starck/video/11-staffel-1-episode-1-partner-wider-willen-ganze-folge',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://www.sat1gold.de/tv/edel-starck/playlist/die-gesamte-1-staffel',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://www.advopedia.de/videos/lenssen-klaert-auf/lenssen-klaert-auf-folge-8-staffel-3-feiertage-und-freie-tage',
+            'only_matching': True,
+        },
     ]
 
     _TOKEN = 'prosieben'
@@ -361,19 +389,28 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
     def _extract_playlist(self, url, webpage):
         playlist_id = self._html_search_regex(
             self._PLAYLIST_ID_REGEXES, webpage, 'playlist id')
-        for regex in self._PLAYLIST_CLIP_REGEXES:
+        playlist = self._parse_json(
-            playlist_clips = re.findall(regex, webpage)
+            self._search_regex(
-            if playlist_clips:
+                'var\s+contentResources\s*=\s*(\[.+?\]);\s*</script',
-                title = self._html_search_regex(
+                webpage, 'playlist'),
-                    self._TITLE_REGEXES, webpage, 'title')
+            playlist_id)
-                description = self._html_search_regex(
+        entries = []
-                    self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
+        for item in playlist:
-                entries = [
+            clip_id = item.get('id') or item.get('upc')
-                    self.url_result(
+            if not clip_id:
-                        re.match('(.+?//.+?)/', url).group(1) + clip_path,
+                continue
-                        'ProSiebenSat1')
+            info = self._extract_video_info(url, clip_id)
-                    for clip_path in playlist_clips]
+            info.update({
-                return self.playlist_result(entries, playlist_id, title, description)
+                'id': clip_id,
+                'title': item.get('title') or item.get('teaser', {}).get('headline'),
+                'description': item.get('teaser', {}).get('description'),
+                'thumbnail': item.get('poster'),
+                'duration': float_or_none(item.get('duration')),
+                'series': item.get('tvShowTitle'),
+                'uploader': item.get('broadcastPublisher'),
+            })
+            entries.append(info)
+        return self.playlist_result(entries, playlist_id)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/soundcloud.py

@@ -53,6 +53,7 @@ class SoundcloudIE(InfoExtractor):
                 'uploader': 'E.T. ExTerrestrial Music',
                 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
                 'duration': 143,
+                'license': 'all-rights-reserved',
             }
         },
         # not streamable song
@@ -66,6 +67,7 @@ class SoundcloudIE(InfoExtractor):
                 'uploader': 'The Royal Concept',
                 'upload_date': '20120521',
                 'duration': 227,
+                'license': 'all-rights-reserved',
             },
             'params': {
                 # rtmp
@@ -84,6 +86,7 @@ class SoundcloudIE(InfoExtractor):
                 'description': 'test chars:  \"\'/\\ä↭',
                 'upload_date': '20131209',
                 'duration': 9,
+                'license': 'all-rights-reserved',
             },
         },
         # private link (alt format)
@@ -98,6 +101,7 @@ class SoundcloudIE(InfoExtractor):
                 'description': 'test chars:  \"\'/\\ä↭',
                 'upload_date': '20131209',
                 'duration': 9,
+                'license': 'all-rights-reserved',
             },
         },
         # downloadable song
@@ -112,6 +116,7 @@ class SoundcloudIE(InfoExtractor):
                 'uploader': 'oddsamples',
                 'upload_date': '20140109',
                 'duration': 17,
+                'license': 'cc-by-sa',
             },
         },
     ]
@@ -138,20 +143,20 @@ class SoundcloudIE(InfoExtractor):
         name = full_title or track_id
         if quiet:
             self.report_extraction(name)
-
+        thumbnail = info.get('artwork_url')
-        thumbnail = info['artwork_url']
+        if isinstance(thumbnail, compat_str):
-        if thumbnail is not None:
             thumbnail = thumbnail.replace('-large', '-t500x500')
         ext = 'mp3'
         result = {
             'id': track_id,
-            'uploader': info['user']['username'],
+            'uploader': info.get('user', {}).get('username'),
-            'upload_date': unified_strdate(info['created_at']),
+            'upload_date': unified_strdate(info.get('created_at')),
             'title': info['title'],
-            'description': info['description'],
+            'description': info.get('description'),
             'thumbnail': thumbnail,
             'duration': int_or_none(info.get('duration'), 1000),
             'webpage_url': info.get('permalink_url'),
+            'license': info.get('license'),
         }
         formats = []
         if info.get('downloadable', False):
@@ -221,7 +226,7 @@ class SoundcloudIE(InfoExtractor):
             raise ExtractorError('Invalid URL: %s' % url)
 
         track_id = mobj.group('track_id')
-        token = None
+
         if track_id is not None:
             info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
             full_title = track_id
@@ -255,7 +260,20 @@ class SoundcloudIE(InfoExtractor):
         return self._extract_info_dict(info, full_title, secret_token=token)
 
 
-class SoundcloudSetIE(SoundcloudIE):
+class SoundcloudPlaylistBaseIE(SoundcloudIE):
+    @staticmethod
+    def _extract_id(e):
+        return compat_str(e['id']) if e.get('id') else None
+
+    def _extract_track_entries(self, tracks):
+        return [
+            self.url_result(
+                track['permalink_url'], SoundcloudIE.ie_key(),
+                video_id=self._extract_id(track))
+            for track in tracks if track.get('permalink_url')]
+
+
+class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
     _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?'
     IE_NAME = 'soundcloud:set'
     _TESTS = [{
@@ -294,7 +312,7 @@ class SoundcloudSetIE(SoundcloudIE):
             msgs = (compat_str(err['error_message']) for err in info['errors'])
             raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
 
-        entries = [self.url_result(track['permalink_url'], 'Soundcloud') for track in info['tracks']]
+        entries = self._extract_track_entries(info['tracks'])
 
         return {
             '_type': 'playlist',
@@ -304,7 +322,7 @@ class SoundcloudSetIE(SoundcloudIE):
         }
 
 
-class SoundcloudUserIE(SoundcloudIE):
+class SoundcloudUserIE(SoundcloudPlaylistBaseIE):
     _VALID_URL = r'''(?x)
                         https?://
                             (?:(?:www|m)\.)?soundcloud\.com/
@@ -321,21 +339,21 @@ class SoundcloudUserIE(SoundcloudIE):
             'id': '114582580',
             'title': 'The Akashic Chronicler (All)',
         },
-        'playlist_mincount': 111,
+        'playlist_mincount': 74,
     }, {
         'url': 'https://soundcloud.com/the-akashic-chronicler/tracks',
         'info_dict': {
             'id': '114582580',
             'title': 'The Akashic Chronicler (Tracks)',
         },
-        'playlist_mincount': 50,
+        'playlist_mincount': 37,
     }, {
         'url': 'https://soundcloud.com/the-akashic-chronicler/sets',
         'info_dict': {
             'id': '114582580',
             'title': 'The Akashic Chronicler (Playlists)',
         },
-        'playlist_mincount': 3,
+        'playlist_mincount': 2,
     }, {
         'url': 'https://soundcloud.com/the-akashic-chronicler/reposts',
         'info_dict': {
@@ -354,7 +372,7 @@ class SoundcloudUserIE(SoundcloudIE):
         'url': 'https://soundcloud.com/grynpyret/spotlight',
         'info_dict': {
             'id': '7098329',
-            'title': 'Grynpyret (Spotlight)',
+            'title': 'GRYNPYRET (Spotlight)',
         },
         'playlist_mincount': 1,
     }]
@@ -416,13 +434,14 @@ class SoundcloudUserIE(SoundcloudIE):
                 for cand in candidates:
                     if isinstance(cand, dict):
                         permalink_url = cand.get('permalink_url')
+                        entry_id = self._extract_id(cand)
                         if permalink_url and permalink_url.startswith('http'):
-                            return permalink_url
+                            return permalink_url, entry_id
 
             for e in collection:
-                permalink_url = resolve_permalink_url((e, e.get('track'), e.get('playlist')))
+                permalink_url, entry_id = resolve_permalink_url((e, e.get('track'), e.get('playlist')))
                 if permalink_url:
-                    entries.append(self.url_result(permalink_url))
+                    entries.append(self.url_result(permalink_url, video_id=entry_id))
 
             next_href = response.get('next_href')
             if not next_href:
@@ -442,7 +461,7 @@ class SoundcloudUserIE(SoundcloudIE):
         }
 
 
-class SoundcloudPlaylistIE(SoundcloudIE):
+class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
     _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
     IE_NAME = 'soundcloud:playlist'
     _TESTS = [{
@@ -472,7 +491,7 @@ class SoundcloudPlaylistIE(SoundcloudIE):
         data = self._download_json(
             base_url + data, playlist_id, 'Downloading playlist')
 
-        entries = [self.url_result(track['permalink_url'], 'Soundcloud') for track in data['tracks']]
+        entries = self._extract_track_entries(data['tracks'])
 
         return {
             '_type': 'playlist',

youtube_dl/extractor/tbs.py

@@ -4,10 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .turner import TurnerBaseIE
-from ..utils import (
+from ..utils import extract_attributes
-    extract_attributes,
-    ExtractorError,
-)
 
 
 class TBSIE(TurnerBaseIE):
@@ -37,10 +34,6 @@ class TBSIE(TurnerBaseIE):
         site = domain[:3]
         webpage = self._download_webpage(url, display_id)
         video_params = extract_attributes(self._search_regex(r'(<[^>]+id="page-video"[^>]*>)', webpage, 'video params'))
-        if video_params.get('isAuthRequired') == 'true':
-            raise ExtractorError(
-                'This video is only available via cable service provider subscription that'
-                ' is not currently supported.', expected=True)
         query = None
         clip_id = video_params.get('clipid')
         if clip_id:
@@ -56,4 +49,8 @@ class TBSIE(TurnerBaseIE):
                     'media_src': 'http://androidhls-secure.cdn.turner.com/%s/big' % site,
                     'tokenizer_src': 'http://www.%s.com/video/processors/services/token_ipadAdobe.do' % domain,
                 },
+            }, {
+                'url': url,
+                'site_name': site.upper(),
+                'auth_required': video_params.get('isAuthRequired') != 'false',
             })

youtube_dl/extractor/thisav.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .jwplatform import JWPlatformBaseIE
+from ..utils import remove_end
 
 
 class ThisAVIE(JWPlatformBaseIE):
@@ -35,7 +36,9 @@ class ThisAVIE(JWPlatformBaseIE):
 
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title')
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'),
+            ' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站')
         video_url = self._html_search_regex(
             r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
         if video_url:

youtube_dl/extractor/trutv.py

@@ -22,9 +22,17 @@ class TruTVIE(TurnerBaseIE):
 
     def _real_extract(self, url):
         path, video_id = re.match(self._VALID_URL, url).groups()
+        auth_required = False
         if path:
             data_src = 'http://www.trutv.com/video/cvp/v2/xml/content.xml?id=%s.xml' % path
         else:
+            webpage = self._download_webpage(url, video_id)
+            video_id = self._search_regex(
+                r"TTV\.TVE\.episodeId\s*=\s*'([^']+)';",
+                webpage, 'video id', default=video_id)
+            auth_required = self._search_regex(
+                r'TTV\.TVE\.authRequired\s*=\s*(true|false);',
+                webpage, 'auth required', default='false') == 'true'
             data_src = 'http://www.trutv.com/tveverywhere/services/cvpXML.do?titleId=' + video_id
         return self._extract_cvp_info(
             data_src, path, {
@@ -32,4 +40,8 @@ class TruTVIE(TurnerBaseIE):
                     'media_src': 'http://androidhls-secure.cdn.turner.com/trutv/big',
                     'tokenizer_src': 'http://www.trutv.com/tveverywhere/processors/services/token_ipadAdobe.do',
                 },
+            }, {
+                'url': url,
+                'site_name': 'truTV',
+                'auth_required': auth_required,
             })

youtube_dl/extractor/turner.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .adobepass import AdobePassIE
 from ..compat import compat_str
 from ..utils import (
     xpath_text,
@@ -16,11 +16,11 @@ from ..utils import (
 )
 
 
-class TurnerBaseIE(InfoExtractor):
+class TurnerBaseIE(AdobePassIE):
     def _extract_timestamp(self, video_data):
         return int_or_none(xpath_attr(video_data, 'dateCreated', 'uts'))
 
-    def _extract_cvp_info(self, data_src, video_id, path_data={}):
+    def _extract_cvp_info(self, data_src, video_id, path_data={}, ap_data={}):
         video_data = self._download_xml(data_src, video_id)
         video_id = video_data.attrib['id']
         title = xpath_text(video_data, 'headline', fatal=True)
@@ -70,11 +70,14 @@ class TurnerBaseIE(InfoExtractor):
                 secure_path = self._search_regex(r'https?://[^/]+(.+/)', video_url, 'secure path') + '*'
                 token = tokens.get(secure_path)
                 if not token:
+                    query = {
+                        'path': secure_path,
+                        'videoId': content_id,
+                    }
+                    if ap_data.get('auth_required'):
+                        query['accessToken'] = self._extract_mvpd_auth(ap_data['url'], video_id, ap_data['site_name'], ap_data['site_name'])
                     auth = self._download_xml(
-                        secure_path_data['tokenizer_src'], video_id, query={
+                        secure_path_data['tokenizer_src'], video_id, query=query)
-                            'path': secure_path,
-                            'videoId': content_id,
-                        })
                     error_msg = xpath_text(auth, 'error/msg')
                     if error_msg:
                         raise ExtractorError(error_msg, expected=True)

youtube_dl/extractor/twitch.py

@@ -400,11 +400,8 @@ class TwitchStreamIE(TwitchBaseIE):
             'kraken/streams/%s' % channel_id, channel_id,
             'Downloading stream JSON').get('stream')
 
-        # Fallback on profile extraction if stream is offline
         if not stream:
-            return self.url_result(
+            raise ExtractorError('%s is offline' % channel_id, expected=True)
-                'http://www.twitch.tv/%s/profile' % channel_id,
-                'TwitchProfile', channel_id)
 
         # Channel name may be typed if different case than the original channel name
         # (e.g. http://www.twitch.tv/TWITCHPLAYSPOKEMON) that will lead to constructing

youtube_dl/extractor/twitter.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     determine_ext,
     float_or_none,
@@ -13,6 +14,8 @@ from ..utils import (
     ExtractorError,
 )
 
+from .periscope import PeriscopeIE
+
 
 class TwitterBaseIE(InfoExtractor):
     def _get_vmap_video_url(self, vmap_url, video_id):
@@ -48,12 +51,12 @@ class TwitterCardIE(TwitterBaseIE):
         },
         {
             'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
-            'md5': 'd4724ffe6d2437886d004fa5de1043b3',
+            'md5': 'b6d9683dd3f48e340ded81c0e917ad46',
             'info_dict': {
                 'id': 'dq4Oj5quskI',
                 'ext': 'mp4',
                 'title': 'Ubuntu 11.10 Overview',
-                'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10...',
+                'description': 'md5:a831e97fa384863d6e26ce48d1c43376',
                 'upload_date': '20111013',
                 'uploader': 'OMG! Ubuntu!',
                 'uploader_id': 'omgubuntu',
@@ -100,12 +103,17 @@ class TwitterCardIE(TwitterBaseIE):
             return self.url_result(iframe_url)
 
         config = self._parse_json(self._html_search_regex(
-            r'data-(?:player-)?config="([^"]+)"', webpage, 'data player config'),
+            r'data-(?:player-)?config="([^"]+)"', webpage,
+            'data player config', default='{}'),
             video_id)
 
         if config.get('source_type') == 'vine':
             return self.url_result(config['player_url'], 'Vine')
 
+        periscope_url = PeriscopeIE._extract_url(webpage)
+        if periscope_url:
+            return self.url_result(periscope_url, PeriscopeIE.ie_key())
+
         def _search_dimensions_in_video_url(a_format, video_url):
             m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
             if m:
@@ -244,10 +252,10 @@ class TwitterIE(InfoExtractor):
         'info_dict': {
             'id': '700207533655363584',
             'ext': 'mp4',
-            'title': 'Donte The Dumbass - BEAT PROD: @suhmeduh #Damndaniel',
+            'title': 'JG - BEAT PROD: @suhmeduh #Damndaniel',
-            'description': 'Donte The Dumbass on Twitter: "BEAT PROD: @suhmeduh  https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
+            'description': 'JG on Twitter: "BEAT PROD: @suhmeduh  https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
             'thumbnail': 're:^https?://.*\.jpg',
-            'uploader': 'Donte The Dumbass',
+            'uploader': 'JG',
             'uploader_id': 'jaydingeer',
         },
         'params': {
@@ -278,6 +286,18 @@ class TwitterIE(InfoExtractor):
         'params': {
             'skip_download': True,  # requires ffmpeg
         },
+    }, {
+        'url': 'https://twitter.com/OPP_HSD/status/779210622571536384',
+        'info_dict': {
+            'id': '1zqKVVlkqLaKB',
+            'ext': 'mp4',
+            'title': 'Sgt Kerry Schmidt - Ontario Provincial Police - Road rage, mischief, assault, rollover and fire in one occurrence',
+            'upload_date': '20160923',
+            'uploader_id': 'OPP_HSD',
+            'uploader': 'Sgt Kerry Schmidt - Ontario Provincial Police',
+            'timestamp': 1474613214,
+        },
+        'add_ie': ['Periscope'],
     }]
 
     def _real_extract(self, url):
@@ -328,13 +348,22 @@ class TwitterIE(InfoExtractor):
             })
             return info
 
+        twitter_card_url = None
         if 'class="PlayableMedia' in webpage:
+            twitter_card_url = '%s//twitter.com/i/videos/tweet/%s' % (self.http_scheme(), twid)
+        else:
+            twitter_card_iframe_url = self._search_regex(
+                r'data-full-card-iframe-url=([\'"])(?P<url>(?:(?!\1).)+)\1',
+                webpage, 'Twitter card iframe URL', default=None, group='url')
+            if twitter_card_iframe_url:
+                twitter_card_url = compat_urlparse.urljoin(url, twitter_card_iframe_url)
+
+        if twitter_card_url:
             info.update({
                 '_type': 'url_transparent',
                 'ie_key': 'TwitterCard',
-                'url': '%s//twitter.com/i/videos/tweet/%s' % (self.http_scheme(), twid),
+                'url': twitter_card_url,
             })
-
             return info
 
         raise ExtractorError('There\'s no video in this tweet.')

youtube_dl/extractor/udemy.py

@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
+    compat_str,
     compat_urllib_request,
     compat_urlparse,
 )
@@ -207,7 +208,7 @@ class UdemyIE(InfoExtractor):
             if youtube_url:
                 return self.url_result(youtube_url, 'Youtube')
 
-        video_id = asset['id']
+        video_id = compat_str(asset['id'])
         thumbnail = asset.get('thumbnail_url') or asset.get('thumbnailUrl')
         duration = float_or_none(asset.get('data', {}).get('duration'))
 

youtube_dl/extractor/ustream.py

@@ -1,15 +1,20 @@
 from __future__ import unicode_literals
 
+import random
 import re
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_str,
     compat_urlparse,
 )
 from ..utils import (
+    encode_data_uri,
     ExtractorError,
     int_or_none,
     float_or_none,
+    mimetype2ext,
+    str_or_none,
 )
 
 
@@ -47,8 +52,108 @@ class UstreamIE(InfoExtractor):
             'id': '10299409',
         },
         'playlist_count': 3,
+    }, {
+        'url': 'http://www.ustream.tv/recorded/91343263',
+        'info_dict': {
+            'id': '91343263',
+            'ext': 'mp4',
+            'title': 'GitHub Universe - General Session - Day 1',
+            'upload_date': '20160914',
+            'description': 'GitHub Universe - General Session - Day 1',
+            'timestamp': 1473872730,
+            'uploader': 'wa0dnskeqkr',
+            'uploader_id': '38977840',
+        },
+        'params': {
+            'skip_download': True,  # m3u8 download
+        },
     }]
 
+    def _get_stream_info(self, url, video_id, app_id_ver, extra_note=None):
+        def num_to_hex(n):
+            return hex(n)[2:]
+
+        rnd = random.randrange
+
+        if not extra_note:
+            extra_note = ''
+
+        conn_info = self._download_json(
+            'http://r%d-1-%s-recorded-lp-live.ums.ustream.tv/1/ustream' % (rnd(1e8), video_id),
+            video_id, note='Downloading connection info' + extra_note,
+            query={
+                'type': 'viewer',
+                'appId': app_id_ver[0],
+                'appVersion': app_id_ver[1],
+                'rsid': '%s:%s' % (num_to_hex(rnd(1e8)), num_to_hex(rnd(1e8))),
+                'rpin': '_rpin.%d' % rnd(1e15),
+                'referrer': url,
+                'media': video_id,
+                'application': 'recorded',
+            })
+        host = conn_info[0]['args'][0]['host']
+        connection_id = conn_info[0]['args'][0]['connectionId']
+
+        return self._download_json(
+            'http://%s/1/ustream?connectionId=%s' % (host, connection_id),
+            video_id, note='Downloading stream info' + extra_note)
+
+    def _get_streams(self, url, video_id, app_id_ver):
+        # Sometimes the return dict does not have 'stream'
+        for trial_count in range(3):
+            stream_info = self._get_stream_info(
+                url, video_id, app_id_ver,
+                extra_note=' (try %d)' % (trial_count + 1) if trial_count > 0 else '')
+            if 'stream' in stream_info[0]['args'][0]:
+                return stream_info[0]['args'][0]['stream']
+        return []
+
+    def _parse_segmented_mp4(self, dash_stream_info):
+        def resolve_dash_template(template, idx, chunk_hash):
+            return template.replace('%', compat_str(idx), 1).replace('%', chunk_hash)
+
+        formats = []
+        for stream in dash_stream_info['streams']:
+            # Use only one provider to avoid too many formats
+            provider = dash_stream_info['providers'][0]
+            fragments = [{
+                'url': resolve_dash_template(
+                    provider['url'] + stream['initUrl'], 0, dash_stream_info['hashes']['0'])
+            }]
+            for idx in range(dash_stream_info['videoLength'] // dash_stream_info['chunkTime']):
+                fragments.append({
+                    'url': resolve_dash_template(
+                        provider['url'] + stream['segmentUrl'], idx,
+                        dash_stream_info['hashes'][compat_str(idx // 10 * 10)])
+                })
+            content_type = stream['contentType']
+            kind = content_type.split('/')[0]
+            f = {
+                'format_id': '-'.join(filter(None, [
+                    'dash', kind, str_or_none(stream.get('bitrate'))])),
+                'protocol': 'http_dash_segments',
+                # TODO: generate a MPD doc for external players?
+                'url': encode_data_uri(b'<MPD/>', 'text/xml'),
+                'ext': mimetype2ext(content_type),
+                'height': stream.get('height'),
+                'width': stream.get('width'),
+                'fragments': fragments,
+            }
+            if kind == 'video':
+                f.update({
+                    'vcodec': stream.get('codec'),
+                    'acodec': 'none',
+                    'vbr': stream.get('bitrate'),
+                })
+            else:
+                f.update({
+                    'vcodec': 'none',
+                    'acodec': stream.get('codec'),
+                    'abr': stream.get('bitrate'),
+                })
+            formats.append(f)
+        return formats
+
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
         video_id = m.group('id')
@@ -86,7 +191,22 @@ class UstreamIE(InfoExtractor):
             'url': video_url,
             'ext': format_id,
             'filesize': filesize,
-        } for format_id, video_url in video['media_urls'].items()]
+        } for format_id, video_url in video['media_urls'].items() if video_url]
+
+        if not formats:
+            hls_streams = self._get_streams(url, video_id, app_id_ver=(11, 2))
+            if hls_streams:
+                # m3u8_native leads to intermittent ContentTooShortError
+                formats.extend(self._extract_m3u8_formats(
+                    hls_streams[0]['url'], video_id, ext='mp4', m3u8_id='hls'))
+
+            '''
+            # DASH streams handling is incomplete as 'url' is missing
+            dash_streams = self._get_streams(url, video_id, app_id_ver=(3, 1))
+            if dash_streams:
+                formats.extend(self._parse_segmented_mp4(dash_streams))
+            '''
+
         self._sort_formats(formats)
 
         description = video.get('description')

youtube_dl/extractor/videomore.py

@@ -84,7 +84,7 @@ class VideomoreIE(InfoExtractor):
     @staticmethod
     def _extract_url(webpage):
         mobj = re.search(
-            r'<object[^>]+data=(["\'])https?://videomore.ru/player\.swf\?.*config=(?P<url>https?://videomore\.ru/(?:[^/]+/)+\d+\.xml).*\1',
+            r'<object[^>]+data=(["\'])https?://videomore\.ru/player\.swf\?.*config=(?P<url>https?://videomore\.ru/(?:[^/]+/)+\d+\.xml).*\1',
             webpage)
         if mobj:
             return mobj.group('url')

youtube_dl/extractor/vyborymos.py

@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+
+
+class VyboryMosIE(InfoExtractor):
+    _VALID_URL = r'https?://vybory\.mos\.ru/(?:#precinct/|account/channels\?.*?\bstation_id=)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://vybory.mos.ru/#precinct/13636',
+        'info_dict': {
+            'id': '13636',
+            'ext': 'mp4',
+            'title': 're:^Участковая избирательная комиссия №2231 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'Россия, Москва, улица Введенского, 32А',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://vybory.mos.ru/account/channels?station_id=13636',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        station_id = self._match_id(url)
+
+        channels = self._download_json(
+            'http://vybory.mos.ru/account/channels?station_id=%s' % station_id,
+            station_id, 'Downloading channels JSON')
+
+        formats = []
+        for cam_num, (sid, hosts, name, _) in enumerate(channels, 1):
+            for num, host in enumerate(hosts, 1):
+                formats.append({
+                    'url': 'http://%s/master.m3u8?sid=%s' % (host, sid),
+                    'ext': 'mp4',
+                    'format_id': 'camera%d-host%d' % (cam_num, num),
+                    'format_note': '%s, %s' % (name, host),
+                })
+
+        info = self._download_json(
+            'http://vybory.mos.ru/json/voting_stations/%s/%s.json'
+            % (compat_str(station_id)[:3], station_id),
+            station_id, 'Downloading station JSON', fatal=False)
+
+        return {
+            'id': station_id,
+            'title': self._live_title(info['name'] if info else station_id),
+            'description': info.get('address'),
+            'is_live': True,
+            'formats': formats,
+        }

youtube_dl/extractor/xfileshare.py

@@ -124,12 +124,14 @@ class XFileShareIE(InfoExtractor):
             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 
         title = (self._search_regex(
-            [r'style="z-index: [0-9]+;">([^<]+)</span>',
+            (r'style="z-index: [0-9]+;">([^<]+)</span>',
              r'<td nowrap>([^<]+)</td>',
              r'h4-fine[^>]*>([^<]+)<',
              r'>Watch (.+) ',
-             r'<h2 class="video-page-head">([^<]+)</h2>'],
+             r'<h2 class="video-page-head">([^<]+)</h2>',
-            webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
+             r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'),  # streamin.to
+            webpage, 'title', default=None) or self._og_search_title(
+            webpage, default=None) or video_id).strip()
 
         def extract_video_url(default=NO_DEFAULT):
             return self._search_regex(

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.09.15'
+__version__ = '2016.09.24'